By J03Fr0st
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Senior reviewer for correctness, readability, architecture, security, performance, and tests.
Security reviewer for trust boundaries, vulnerabilities, secrets, dependencies, and release risk.
Test strategy reviewer for coverage gaps, regression risk, and verification evidence.
Web performance reviewer for Core Web Vitals, loading, rendering, and network efficiency.
Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
Use when creative work needs shaping before implementation: creating features, building components, adding functionality, or modifying behavior.
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.
Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Mithril is a curated engineering workflow pack for coding agents. It gives an agent one active router, a set of lifecycle skills, a small command surface, and advisory reviewer personas.
It is not a bulk prompt import. Mithril keeps the layers separate:
Skill = the how.
Persona = the who.
Command = the when.
The user or command orchestrates composition. Personas do not invoke other personas.
DEFINE/SPEC PLAN BUILD VERIFY/DEBUG REVIEW SHIP
Idea + scope -> tasks + gates -> implementation -> proof + traces -> quality gate -> release
/spec /plan /build /test /review /ship
Mithril starts with skills/using-mithril/SKILL.md. That router maps intent to the right Mithril-owned skill and keeps external routers out of the active path.
| Phase | Primary skills |
|---|---|
| Define/spec | brainstorming, grill-me, grill-with-docs, domain-modeling |
| Plan | writing-plans, to-prd, to-issues, triage |
| Build | subagent-driven-development, executing-plans, test-driven-development, implementation-standards |
| Verify/debug | systematic-debugging, browser-testing-with-devtools, observability-and-instrumentation |
| Review | code-review-and-quality, simplicity-review, security-and-hardening, performance-optimization |
| Ship | shipping-and-launch, finishing-a-development-branch, ci-cd-and-automation, documentation-and-adrs |
Commands are entry points. They do not replace skills; they choose when a workflow starts.
| Command | Use it for | Main route |
|---|---|---|
/spec | Shape a request into an approved design | brainstorming |
/plan | Turn an approved design into verifiable tasks | writing-plans |
/build | Execute the next approved slice | subagent-driven-development or executing-plans |
/test | Run the test-first proof loop | test-driven-development |
/review | Review the current change | code-review-and-quality |
/ship | Run launch readiness and merge specialist reports | shipping-and-launch |
/webperf | Audit browser-facing performance evidence | web-performance-auditor |
/standards | Inspect local implementation standards | implementation-standards |
/code-simplify | Simplify working code without behavior changes | code-simplification |
/simplicity | Choose the smallest correct implementation shape | simplicity |
/simplicity-review | Review a diff for avoidable complexity | simplicity-review |
/simplicity-audit | Audit a larger area for removable complexity | simplicity-audit |
Personas are advisory leaf reviewers. They report back to the command or main agent and do not edit files, mutate external systems, or invoke other personas.
| Persona | Perspective |
|---|---|
code-reviewer | Correctness, readability, architecture, tests, security, and performance |
security-auditor | Trust boundaries, secrets, auth, dependencies, and release risk |
test-engineer | Coverage gaps, regression risk, and verification evidence |
web-performance-auditor | Core Web Vitals, loading, rendering, and network efficiency |
See docs/agents.md for composition rules.
Install Mithril separately for each host you use. Start with the host-specific guide:
| Host | Guide |
|---|---|
| Claude Code | docs/claude-code-setup.md |
| Codex | docs/codex-setup.md |
| GitHub Copilot | docs/copilot-setup.md |
| Cursor | docs/cursor-setup.md |
| Gemini CLI | docs/gemini-cli-setup.md |
| OpenCode | docs/opencode-setup.md |
| Windsurf | docs/windsurf-setup.md |
Universal setup is covered in docs/getting-started.md.
skills/ Mithril workflows, one SKILL.md per skill
commands/ Command TOML files
agents/ Advisory reviewer personas
references/ Checklists and orchestration references
docs/ Public docs, setup guides, and design/spec artifacts
hooks/ Host lifecycle hooks
scripts/ Validation and packaging helpers
MITHRIL_* environment variable names in Mithril-facing docs and companion tooling. MITHRIL_DISABLE_TELEMETRY disables optional Mithril companion telemetry when present.Agent workflow kit for brainstorming, domain-doc grilling, dated specs, implementation Phases, TDD, debugging, review, and delivery.
npx claudepluginhub j03fr0st/mithril --plugin mithrilCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Harness-native ECC plugin for engineering teams - 67 agents, 277 skills, 93 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Supergraph enforces a complete, evidence-based coding pipeline — scan → plan → TDD → fix → verify → review — grounded in real codebase analysis at every step. It combines AST dependency graphs, LSP-level code intelligence, and a structured skill chain so Claude never guesses about impact before making a change.
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development